AdvRush
Official Code for AdvRush: Searching for Adversarially Robust Neural Architectures (ICCV '21)
Environmental Set-up
Python == 3.6.12, PyTorch == 1.2.0, torchvision == 0.4.0
AdvRush Search Process
cd advrush && python train_search.py --batch_size 32 --gpu 0 --epochs 60 --a_gamma 0.01 --a_warmup_epochs 0 --w_warmup_epochs 60 --loss_hessian loss_cure
Adversarial Training
cd advrush && python adv_train.py --batch_size 64 --gpu 0 --epochs 200 --adv_loss pgd --arch ADVRUSH
Evaluation under PGD Attack
Prior to the evaluation process, add all necessary checkpoint files (preferably in the form of .pth.tar) to the /eval/checkpoints folder. To conduct white-box attacks,
cd eval &&
python pgd_attack.py --white-box-attack True --test-batch-size 10 --arch [arch_name] --checkpoint [./checkpoints/file_name.pth.tar] --data_type [cifar10/svhn]
To conduct black-box attacks,
cd eval &&
python pgd_attack.py --test-batch-size 10 --target_arch [target_arch] --target_checkpoint [./checkpoints/target_file.pth.tar] --source_arch [source_arch] --source_checkpoint [./checkpoints/source_file.pth.tar] --data_type cifar10
References
DARTS: Differentiable Architecture Search [ICLR '19] code paper
Robustness via Curvature Regularization, and Vice Versa [CVPR '19] code paper
Tradeoff-inspired Adversarial Defense via Surrogate-loss Minimization [ICML '19] code paper
78 Dec 29, 2022
25 Dec 21, 2022
12 Dec 14, 2022
10 Jan 10, 2022
550 Dec 21, 2022
2 Jan 15, 2022
81 Dec 16, 2022
146 Jan 06, 2023
139 Dec 20, 2022
10 Nov 09, 2022
68 Sep 05, 2022
77 Jan 03, 2023
56 Dec 23, 2022
3 May 28, 2021
65 Sep 12, 2022
4 Oct 29, 2022
72 Jan 01, 2023
45 Dec 26, 2022
361 Dec 12, 2022
65 Dec 26, 2022